All AI models · LLM benchmarks · Methodology

Echo

Adaptive model for coding, reasoning, and tool-driven agent workflows through one OpenAI-compatible endpoint

Model facts

Context window
262K tokens
Maximum output
66K tokens
Cheapest paid input
$10 per 1M tokens
Cheapest paid output
$50 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, tool calling, temperature control, text.

Observed price history

  • 2026-08-24: $10 input / $50 output per 1M tokens

API providers